{"as_of":"2026-08-10T20:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:27861d20fabfd399f3b11ab3601885525689f9163323bd82b8ea00cf31831555","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T14:18:41.459635Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.01854/citation-record","integrity":"/paper/2502.01854/integrity","json":"/paper/2502.01854/citation-record.json","paper":"/paper/2502.01854"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.354931Z","title":"AMP- Inspired Deep Networks for Sparse Linear Inverse Prob- lems","venue":null,"work_id":"f7595366-d180-40d3-a638-52c71663ec18","year":2017},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.129636Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:2462642015027ea4278dcc94820d92c515a13174fa16b11c63858c83ca7a6c08","observation_id":"f836bc26-a9bf-4b05-8c1e-867b9c2a24d2","resolution":{"observed_at":"2026-08-09T14:18:43.359048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.343218Z","title":"ISTA-Net: Interpretable optimization-inspired deep network for image com- pressive sensing","venue":null,"work_id":"d1f8b7dc-a39f-4008-b13c-f2b07bdbef45","year":2018},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.162969Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:5a4148f4e880f6d1257f8f84bd6734fe91eb3b7fa922b983f94eec0308e6879c","observation_id":"0a4b0e5e-ff44-4c65-8e28-af99665a1320","resolution":{"observed_at":"2026-08-09T14:18:43.346837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.330261Z","title":"ADMM-CSNet: A deep learning ap- proach for image compressive sensing","venue":null,"work_id":"91f95055-007e-4d6a-97f3-ba38c214af64","year":2018},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.167356Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:fe5607bb70c33af87fb4654e1934d24842f14d7fb4f7dd8926a8f1ae35afcf5b","observation_id":"78a85fa6-1099-4f98-8a12-631e7d8a1c39","resolution":{"observed_at":"2026-08-09T14:18:43.334281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.319037Z","title":"Model-based deep learning","venue":null,"work_id":"d45a32de-db72-4e5c-90c7-1f7d4b6c2a11","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.170391Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:946da46a34ab606ab30797087e7df5be6d3078f00c80552695dcde7c2ca3bf5f","observation_id":"93b79a22-06d3-4d4f-b4dc-53788836d428","resolution":{"observed_at":"2026-08-09T14:18:43.322279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.244714Z","title":"Star DGT: a robust Gabor transform for speech denoising","venue":null,"work_id":"247a7cc8-77f9-46fd-8b7a-e1b5f3433845","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.174086Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:078970798f3774555b59ce79258231e3016342618177b8e83f68524fa66b6024","observation_id":"dcc20eea-885d-421a-aeab-0d14e4d9fe40","resolution":{"observed_at":"2026-08-09T14:18:43.309530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:43.086508Z","title":"ASCONVSR: Fast and lightweight super- resolution network with assembled convolutions","venue":null,"work_id":"0829d94d-808b-42fc-bee6-59c9fb5f4450","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.177908Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:c9faf81b29ae4ed29e1ac29e495637786580520b5ab67d91d2f6125444037e9d","observation_id":"aa5f8340-c4cb-4c08-8809-221a94b970ee","resolution":{"observed_at":"2026-08-09T14:18:43.165699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.936862Z","title":"Pansharpening method based on deep nonlocal unfolding","venue":null,"work_id":"20b99b4b-344a-417f-b6e0-01416c9e41b1","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.182074Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:1e5f29f97483287ead20393971e7f80362a69ed16da775680bf63266d42acb83","observation_id":"d45ecc26-006c-4ed5-8372-2931f91a6a8a","resolution":{"observed_at":"2026-08-09T14:18:43.060275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.881221Z","title":"A Deep Proximal-Unfolding Method for Monaural Speech Dereverberation","venue":null,"work_id":"fb237e58-36e2-4dbb-b0f6-46f808e6a7a0","year":2022},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.185674Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:fe428db2cf5b7e503ac71347fb19379c033a95791136aaaf367bc459f67a23bd","observation_id":"d1748ba7-5709-498b-8c5e-451360ee4ea6","resolution":{"observed_at":"2026-08-09T14:18:42.895994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.867348Z","title":"Model-based compressive sens- ing","venue":null,"work_id":"a3b62e0a-4d13-4bd4-bad5-a5ae256ae4a6","year":2010},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.189829Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:c207f36a1d533ad5f3bc0264cd44dc0f834f2116c14ff32ae3eb8e016b2cfce2","observation_id":"04334939-b454-41fa-9bd0-1692966da530","resolution":{"observed_at":"2026-08-09T14:18:42.872039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.855170Z","title":"Spark Deficient Gabor Frame Provides a Novel Analysis Operator for Compressed Sensing","venue":null,"work_id":"b7cd5b3f-8198-442d-8100-2e7aef583056","year":2021},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.195337Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:fd4a552995c77e737d2b99e717919da37fe05786e0392a7088a87833d0b8e006","observation_id":"b52dfdfe-bcae-445c-98e6-0b7e8073512b","resolution":{"observed_at":"2026-08-09T14:18:42.859169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:41.761288Z","title":"DECONET: an Unfolding Network for Analysis-based Compressed Sensing with Generalization Error Bounds","venue":null,"work_id":"5521ac6a-363e-46cf-89a9-cae86dbc73af","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.198903Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:2866ef8e6de66c7ca972576069b1bdb6ac752ca95b0271829c0b272a344e4dce","observation_id":"0e024168-462e-4c55-9f51-6e5410709971","resolution":{"observed_at":"2026-08-09T14:18:41.806139Z","resolver_source":"arxiv_id_nonexistent","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05582","last_updated":"2025-06-10T15:26:36Z","snapshot_observed_at":"2026-07-06T15:01:02.435666Z","submitted_at":"2023-03-09T21:13:32Z","title":"Generalization analysis of an unfolding network for analysis-based Compressed Sensing","version":3},"cited_work":{"arxiv_id":"2303.05582","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.05582","snapshot_observed_at":"2026-08-09T14:18:41.563466Z","title":"Generalization analysis of an unfolding network for analysis-based Compressed Sensing","venue":"cs.LG","work_id":"fd082a36-34cb-4fc4-a9aa-750749853ff8","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.202429Z"},"links":{"cited_paper":"/paper/2303.05582","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:7acad87db995ad7e9686ab53ddcc89446fc587fafc9674b85e0c9fb8c176a663","observation_id":"815dca34-6863-4951-8305-cf85ad98baef","resolution":{"observed_at":"2026-08-09T14:18:41.568152Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.831865Z","title":"Artificial neural networks for nonlinear regression and classification","venue":null,"work_id":"ce7b8a15-8ec6-4b04-a3a6-8d3045f1e6ea","year":2010},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.206304Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:3db495dabc6c8fd8c90541fa8a828684f65e358725f489935f5abe78f648a5c3","observation_id":"edfbc758-6a05-4e35-b84e-90c1520a8971","resolution":{"observed_at":"2026-08-09T14:18:42.842083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.819282Z","title":"Dr2-net: Deep residual reconstruction network for image compressive sensing","venue":null,"work_id":"68997a64-a0e2-4162-85af-883d2b98e930","year":2019},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.209815Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:921a7887e8faecf165a772d637c193fb7ad49be14e7c4fc4bc1b4a82dbcdeefb","observation_id":"6d52bc8e-38d3-44b6-9a27-0c40bc6437c8","resolution":{"observed_at":"2026-08-09T14:18:42.823132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.805477Z","title":"A residual dense u-net neural network for image denois- ing","venue":null,"work_id":"bcae3182-fc93-4c70-a5d6-aed90dc16b5d","year":2021},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.213167Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:525b3faf116563adca610cbd4dc0152d6c60ac65e1f51d429136a6dca19f76d3","observation_id":"9e24704f-c4be-4628-aa9d-3dfc3b6a6443","resolution":{"observed_at":"2026-08-09T14:18:42.810488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.789274Z","title":"Designing interpretable recurrent neural networks for video reconstruction via deep un- folding","venue":null,"work_id":"df3a8a60-29ac-474a-8579-3500158f6e3d","year":2021},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.217205Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:e64aecb11ea74995499f61280f9cdde8e3684f77aa1e1b41c23e5c795c5d161d","observation_id":"da362893-07da-424b-805d-0ea9a326277d","resolution":{"observed_at":"2026-08-09T14:18:42.794583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.776335Z","title":"AMP-Net: Denoising-Based Deep Unfolding for Compressive Image Sensing","venue":null,"work_id":"9c97d540-bcb8-461d-8f4b-e430a8477e96","year":2021},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.220646Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:71b8c55f5d468cb0b21cc63a864db9e0ee12efcfc3b3c246e392fb0831d2b6ca","observation_id":"e2277403-4df6-4a66-8648-a13e9c38cdd3","resolution":{"observed_at":"2026-08-09T14:18:42.780608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.761605Z","title":"Dynamic path- controllable deep unfolding network for compressive sensing","venue":null,"work_id":"3202e6aa-8144-498c-9e05-1e3c4af6c413","year":2023},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.224315Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:6b760011b6a25c914f611b5b74dbf9228025dd770538aac06c8a067024c3fc8e","observation_id":"80a5547f-3d06-4d5f-926f-c314ba70393b","resolution":{"observed_at":"2026-08-09T14:18:42.765274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.749207Z","title":"Gates-Controlled Deep Unfolding Network for Image Compressed Sensing","venue":null,"work_id":"0783b62c-7107-4eca-8b49-2fb66b2dc2f8","year":2024},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.229331Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:fc7d7aad08c7d9f71d7148b67e2bb404e8f7463d5ed0d2d060f694b97636f905","observation_id":"57379422-f609-4df4-a46c-ff2019936ca1","resolution":{"observed_at":"2026-08-09T14:18:42.753642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.649210Z","title":"UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing","venue":null,"work_id":"aafc5146-b6af-49e7-a8f3-e5828a95cfbf","year":2024},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.232881Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:06b78e70e56bdef52f81c510919226949286bdca58a740fdbb2a0bf5b44b16fc","observation_id":"3870675e-45d9-48d7-9ad7-fb6b80c92141","resolution":{"observed_at":"2026-08-09T14:18:42.740359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.492376Z","title":"Deep unfolding with normalizing flow priors for inverse problems","venue":null,"work_id":"516c2b77-198d-4456-b9d4-253569746cc6","year":2022},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.236908Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:7f73b217857a4327ba4b0f6542afd2c47ae47a94bc612c6549948b6a835a8443","observation_id":"88723057-a5ab-416e-91ed-810304203dff","resolution":{"observed_at":"2026-08-09T14:18:42.574170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.376283Z","title":"A fixed-point continuation method for l1-regularized minimization with applications to compressed sensing","venue":null,"work_id":"54a8e33d-543c-4ad9-b184-e98954299846","year":2007},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.240782Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:044c3c266f707caa3ef4168caa7bb34efce999ad8f8b679e78fb3e42cdf07193","observation_id":"ab6b8840-e560-4f2b-bc7d-94527501b476","resolution":{"observed_at":"2026-08-09T14:18:42.430267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.328413Z","title":"Fixed-point contin- uation for ℓ1-minimization: Methodology and conver- gence","venue":null,"work_id":"4f1a1509-53b8-4323-923c-b8e5152bc37c","year":2008},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.244255Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:93fd75f743228e414a46aaff079b06aa8a7907f022f4ee9422ae2d08ca78920f","observation_id":"c644a98e-3b00-4c22-8233-594dbd2ca042","resolution":{"observed_at":"2026-08-09T14:18:42.332484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.317610Z","title":"NESTA: A fast and accurate first-order method for sparse recovery","venue":null,"work_id":"201bf374-dd8e-49c0-a146-a7016e66af36","year":2011},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.247520Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:8aa8cfe78c602988d8be1c0f5a3ad061086aedcf5c8bb96583f390d6ec00048d","observation_id":"326f3dd5-461d-43e8-9c7d-a1630b55b46b","resolution":{"observed_at":"2026-08-09T14:18:42.321139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.305793Z","title":"Fast ℓ1-Minimization Algorithms for Robust Face Recognition","venue":null,"work_id":"eec30e8a-c1e2-465c-98cd-0b2ee7ea2064","year":2013},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.251724Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:db70165b517fb44092f96832eff9ad591b6da6778b297bbdd484c9fea3218586","observation_id":"67fc63f0-263f-4738-8857-dacb71c1ff5c","resolution":{"observed_at":"2026-08-09T14:18:42.309734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.293407Z","title":"Warm-start strategies in interior-point methods for linear programming","venue":null,"work_id":"c71bb94a-1d93-4b5f-bc80-8a4846570378","year":2002},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.255074Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:f9363895b21cd200e7c9dc3a07ed1f7c8decc10f67350b8dd7ac32b17f2cacdd","observation_id":"175756ab-5e20-4e17-aa84-dce23dc437ef","resolution":{"observed_at":"2026-08-09T14:18:42.297953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.280198Z","title":"On warm starts for interior methods","venue":null,"work_id":"23385a6b-72b3-4caa-8c3e-c6f0cc5939b7","year":2005},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.312238Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:c162d7e5756689556c3c61c3a21c0cbcd2b1c4dd7269ac14ec5f8f20d99c6309","observation_id":"45946119-6375-449c-9570-d12cb960bccb","resolution":{"observed_at":"2026-08-09T14:18:42.285065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.267263Z","title":"Templates for convex cone problems with applications to sparse signal recovery","venue":null,"work_id":"1deb94b2-f410-4291-805b-edad9d359283","year":2011},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.328978Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:6bf0aba7dc48b3268cc07d7ae07ac5ac2687323174471ee70fdb6811dab569bb","observation_id":"b5c9875b-56d5-4e89-a539-fda653b7fa5b","resolution":{"observed_at":"2026-08-09T14:18:42.270969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04608","last_updated":"2025-01-10T03:08:11Z","snapshot_observed_at":"2026-08-04T12:40:50.098204Z","submitted_at":"2025-01-08T16:44:06Z","title":"Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems","version":2},"cited_work":{"arxiv_id":"2501.04608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.04608","snapshot_observed_at":"2026-08-09T14:18:41.545503Z","title":"Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems","venue":"eess.IV","work_id":"60cff47a-97b7-4dc5-8285-6e670b345c2e","year":2025},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.363598Z"},"links":{"cited_paper":"/paper/2501.04608","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:5cdfa01026890d30cc79b70a3534d2fad8da8d13dc0c8498438741b80cbe3360","observation_id":"bab3a3ca-2f6e-43cb-ac2f-babb867163d6","resolution":{"observed_at":"2026-08-09T14:18:41.550065Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.255031Z","title":"Denoiser-Regulated Deep Unfolding Compressed Sensing with Learnable Fixed-Point Pro- jections","venue":null,"work_id":"3db9384e-5783-4d1e-aad3-2d6081f55b67","year":2024},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.405190Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:e67f0cc537b01ecb8299d6c225b1d1cfdecd5e7d1b7af0f71ebd703ab4561e45","observation_id":"53f41134-0249-4ddb-a631-00af589375af","resolution":{"observed_at":"2026-08-09T14:18:42.259753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.240995Z","title":"Generalization error bounds for deep unfolding RNNs","venue":null,"work_id":"b478a54f-5a66-4795-8f71-62e224bf102d","year":2021},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.422140Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:af9504e0c6236deb4bdf52bdcf43443a73ce67112a8b9de21e034c96539b3390","observation_id":"572e4047-f169-4737-bc15-eb1dc1014b09","resolution":{"observed_at":"2026-08-09T14:18:42.245579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13106","last_updated":"2024-02-20T16:01:39Z","snapshot_observed_at":"2026-07-06T17:32:56.445791Z","submitted_at":"2024-02-20T16:01:39Z","title":"On Generalization Bounds for Deep Compound Gaussian Neural Networks","version":1},"cited_work":{"arxiv_id":"2402.13106","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.13106","snapshot_observed_at":"2026-08-09T14:18:41.524935Z","title":"On Generalization Bounds for Deep Compound Gaussian Neural Networks","venue":"stat.ML","work_id":"0f1548ad-42b9-41d0-9f26-50005c549096","year":2024},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.426414Z"},"links":{"cited_paper":"/paper/2402.13106","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:93224ee1c48dd6927544b7d5725ac06722ab8bf17656c02c5b10138489a4a102","observation_id":"1e73e999-c2f8-4753-8a0d-caebd8069bbc","resolution":{"observed_at":"2026-08-09T14:18:41.531130Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.228899Z","title":"A comprehensive survey of regression-based loss functions for time series forecasting","venue":null,"work_id":"9648ce8d-1273-4d0f-8cf5-1376cc813c1b","year":2024},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.429592Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:e1a212dd83e2fa53f5da866ac70a61d23e5486a8f42cb56994a42f6900c2f7e5","observation_id":"c79d7a55-ddeb-4f42-be3e-cf2ff1433bbf","resolution":{"observed_at":"2026-08-09T14:18:42.233624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.04564","last_updated":"2024-03-15T21:58:47Z","snapshot_observed_at":"2026-08-06T05:11:51.218667Z","submitted_at":"2022-08-09T07:03:58Z","title":"Statistical Properties of the log-cosh Loss Function Used in Machine Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.04564","snapshot_observed_at":"2026-08-09T14:18:41.433771Z","title":"Statistical properties of the log-cosh loss function used in machine learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.433771Z"},"links":{"cited_paper":"/paper/2208.04564","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:48c39b51eeb3a67f1d24a92a3ddee25d04b3e8ecb5b9c1f4c635be04e52f5227","observation_id":"ba770263-12f2-48cf-93b8-629fa1823332","resolution":{"observed_at":"2026-08-09T14:18:41.433771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.216140Z","title":"Visualizing the loss landscape of neural nets","venue":null,"work_id":"d709d562-c5c3-47b5-bab5-3cbf06a37634","year":2018},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.437193Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:3edf1d954214b2e7fc5d82e434e6838d5ec925d59647c35dee00da0fbfa32fe4","observation_id":"adce2174-639c-4f2e-a356-8c4e258c6085","resolution":{"observed_at":"2026-08-09T14:18:42.220336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.203968Z","title":"A deep unfolding method for satellite super resolution","venue":null,"work_id":"2b200bf3-4eab-48bb-87f7-d8d5101cd7b8","year":2022},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.440749Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:e043af6b903b26b9a71e6dde013fde1475a1dc1fcd20130930055733040a16c9","observation_id":"1db7d429-a3a7-424c-8680-1b67f2dcc755","resolution":{"observed_at":"2026-08-09T14:18:42.208461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.06733","last_updated":"2020-10-21T19:19:02Z","snapshot_observed_at":"2026-08-10T17:19:33.952728Z","submitted_at":"2019-03-15T18:23:55Z","title":"Dying ReLU and Initialization: Theory and Numerical Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.06733","snapshot_observed_at":"2026-08-09T14:18:41.445166Z","title":"Dying relu and initialization: The- ory and numerical examples","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.445166Z"},"links":{"cited_paper":"/paper/1903.06733","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:c11c042dc73ac29f537d2225c2ba1123a2101a1dd7df888ee2bc017ca835a9ab","observation_id":"0e6062f9-d2ed-4555-9e91-8f8cfaf0f8b4","resolution":{"observed_at":"2026-08-09T14:18:41.445166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.191235Z","title":"Introduction to pytorch","venue":null,"work_id":"8d9ee624-1fca-4033-9774-7c38275c881f","year":2017},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.449138Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:4e872eeadfb90e3ce03779a94868c9ac335f45d01390008ed61d6c3c7e544305","observation_id":"7c72aaab-7229-4072-95b0-384445b6fdbb","resolution":{"observed_at":"2026-08-09T14:18:42.195569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-09T14:18:41.452099Z","title":"Adam: A method for stochas- tic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.452099Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:f517923a98baef73d2d4d361ce5063953b14a3f0eed312cb1950a2884116a1bc","observation_id":"a52315cf-6dd5-4f1d-952a-d8b9edac3cbe","resolution":{"observed_at":"2026-08-09T14:18:41.452099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:42.039992Z","title":"Early stopping-but when?","venue":null,"work_id":"ba1a8723-d017-4eb0-92b4-8a870f6affd4","year":1998},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.456025Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:025ad25446c226566bf960588b9a61ab181327c30e4f495e071293a511e3e8d1","observation_id":"1017872c-b0d8-408f-8a95-7839ccbaff85","resolution":{"observed_at":"2026-08-09T14:18:42.088939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:18:41.868326Z","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","venue":null,"work_id":"3ae2499d-8bd1-437a-ad39-3cd88a475b77","year":2022},"citing_paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T14:18:41.459635Z"},"links":{"citing_paper":"/paper/2502.01854"},"observation_digest":"sha256:1ccd2df833e4135b48be4ccda7126d33e80c650e03109befa6408bad11c8d2df","observation_id":"8ad9ca1d-4868-4fec-908d-94bfdbce32fd","resolution":{"observed_at":"2026-08-09T14:18:41.919823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.01854","last_updated":"2025-02-07T12:56:30Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T07:11:10.768800Z","submitted_at":"2025-02-03T22:05:45Z","title":"How to warm-start your unfolding network"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":3,"verified_fuzzy":34},"total_outbound_references":41},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2502.01854."}